MCPcopy Create free account
hub / github.com/MoonInTheRiver/DiffSinger / FastspeechDecoder

Class FastspeechDecoder

modules/fastspeech/tts_modules.py:347–353  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

345
346
347class FastspeechDecoder(FFTBlocks):
348 def __init__(self, hidden_size=None, num_layers=None, kernel_size=None, num_heads=None):
349 num_heads = hparams['num_heads'] if num_heads is None else num_heads
350 hidden_size = hparams['hidden_size'] if hidden_size is None else hidden_size
351 kernel_size = hparams['dec_ffn_kernel_size'] if kernel_size is None else kernel_size
352 num_layers = hparams['dec_layers'] if num_layers is None else num_layers
353 super().__init__(hidden_size, num_layers, kernel_size, num_heads=num_heads)
354

Callers 1

fs2.pyFile · 0.90

Calls

no outgoing calls

Tested by

no test coverage detected